Distributed utilization control for real-time clusters with load balancing

Yong Fu; Hongan Wang; Chenyang Lu; Ramu Sharat Chandra

doi:10.1109/RTSS.2006.20

Distributed utilization control for real-time clusters with load balancing

Yong Fu
, Hongan Wang
, Chenyang Lu
, Ramu Sharat Chandra

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

27 Scopus citations

Abstract

Recent years have seen rapid growth of online services that rely on large-scale server clusters to handle high volume of requests. Such clusters must adaptively control the CPU utilizations of many processors in order to maintain desired soft real-time performance and prevent system overload in face of unpredictable workloads, This paper presents DUC-LB, a novel distributed utilization control algorithm for cluster-based soft real-time applications. Compared to earlier works on utilization control, a distinguishing feature of DUC-LB is its capability to handle system dynamics caused by load balancing, which is a common and essential component of most clusters today. Simulation results and control-theoretic analysis demonstrate that DUCLB can provide robust utilization control and effective load balancing in large-scale clusters.

Original language	English
Title of host publication	Proceedings of 27th IEEE International Real-Time Systems Symposium, RTSS 2006
Pages	137-146
Number of pages	10
DOIs	https://doi.org/10.1109/RTSS.2006.20
State	Published - 2006
Event	27th IEEE International Real-Time Systems Symposium, RTSS 2006 - Rio de Janeiro, Brazil Duration: Dec 5 2006 → Dec 8 2006

Publication series

Name	Proceedings - Real-Time Systems Symposium
ISSN (Print)	1052-8725

Conference

Conference	27th IEEE International Real-Time Systems Symposium, RTSS 2006
Country/Territory	Brazil
City	Rio de Janeiro
Period	12/5/06 → 12/8/06

Access to Document

10.1109/RTSS.2006.20

Cite this

@inproceedings{b6837d278f4445d9a64f538a994c8d5a,

title = "Distributed utilization control for real-time clusters with load balancing",

abstract = "Recent years have seen rapid growth of online services that rely on large-scale server clusters to handle high volume of requests. Such clusters must adaptively control the CPU utilizations of many processors in order to maintain desired soft real-time performance and prevent system overload in face of unpredictable workloads, This paper presents DUC-LB, a novel distributed utilization control algorithm for cluster-based soft real-time applications. Compared to earlier works on utilization control, a distinguishing feature of DUC-LB is its capability to handle system dynamics caused by load balancing, which is a common and essential component of most clusters today. Simulation results and control-theoretic analysis demonstrate that DUCLB can provide robust utilization control and effective load balancing in large-scale clusters.",

author = "Yong Fu and Hongan Wang and Chenyang Lu and Chandra, \{Ramu Sharat\}",

year = "2006",

doi = "10.1109/RTSS.2006.20",

language = "English",

isbn = "0769527612",

series = "Proceedings - Real-Time Systems Symposium",

pages = "137--146",

booktitle = "Proceedings of 27th IEEE International Real-Time Systems Symposium, RTSS 2006",

note = "27th IEEE International Real-Time Systems Symposium, RTSS 2006 ; Conference date: 05-12-2006 Through 08-12-2006",

}

Fu, Y, Wang, H, Lu, C & Chandra, RS 2006, Distributed utilization control for real-time clusters with load balancing. in Proceedings of 27th IEEE International Real-Time Systems Symposium, RTSS 2006., 4032343, Proceedings - Real-Time Systems Symposium, pp. 137-146, 27th IEEE International Real-Time Systems Symposium, RTSS 2006, Rio de Janeiro, Brazil, 12/5/06. https://doi.org/10.1109/RTSS.2006.20

Distributed utilization control for real-time clusters with load balancing. / Fu, Yong; Wang, Hongan; Lu, Chenyang et al.
Proceedings of 27th IEEE International Real-Time Systems Symposium, RTSS 2006. 2006. p. 137-146 4032343 (Proceedings - Real-Time Systems Symposium).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Distributed utilization control for real-time clusters with load balancing

AU - Fu, Yong

AU - Wang, Hongan

AU - Lu, Chenyang

AU - Chandra, Ramu Sharat

PY - 2006

Y1 - 2006

N2 - Recent years have seen rapid growth of online services that rely on large-scale server clusters to handle high volume of requests. Such clusters must adaptively control the CPU utilizations of many processors in order to maintain desired soft real-time performance and prevent system overload in face of unpredictable workloads, This paper presents DUC-LB, a novel distributed utilization control algorithm for cluster-based soft real-time applications. Compared to earlier works on utilization control, a distinguishing feature of DUC-LB is its capability to handle system dynamics caused by load balancing, which is a common and essential component of most clusters today. Simulation results and control-theoretic analysis demonstrate that DUCLB can provide robust utilization control and effective load balancing in large-scale clusters.

AB - Recent years have seen rapid growth of online services that rely on large-scale server clusters to handle high volume of requests. Such clusters must adaptively control the CPU utilizations of many processors in order to maintain desired soft real-time performance and prevent system overload in face of unpredictable workloads, This paper presents DUC-LB, a novel distributed utilization control algorithm for cluster-based soft real-time applications. Compared to earlier works on utilization control, a distinguishing feature of DUC-LB is its capability to handle system dynamics caused by load balancing, which is a common and essential component of most clusters today. Simulation results and control-theoretic analysis demonstrate that DUCLB can provide robust utilization control and effective load balancing in large-scale clusters.

UR - https://www.scopus.com/pages/publications/38949189628

U2 - 10.1109/RTSS.2006.20

DO - 10.1109/RTSS.2006.20

M3 - Conference contribution

AN - SCOPUS:38949189628

SN - 0769527612

SN - 9780769527611

T3 - Proceedings - Real-Time Systems Symposium

SP - 137

EP - 146

BT - Proceedings of 27th IEEE International Real-Time Systems Symposium, RTSS 2006

T2 - 27th IEEE International Real-Time Systems Symposium, RTSS 2006

Y2 - 5 December 2006 through 8 December 2006

ER -

Distributed utilization control for real-time clusters with load balancing

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this